skills/qwenlm/qwen-code/feat-dev/Gen Agent Trust Hub

feat-dev

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill instructions describe a legitimate software development process including design, testing, and implementation using standard local tools. No malicious patterns or security vulnerabilities were detected.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands for building, type-checking, and bundling the local project.
  • Evidence: The workflow includes commands npm run build, npm run typecheck, npm run bundle, and node dist/cli.js (SKILL.md).
  • [PROMPT_INJECTION]: The workflow involves ingesting data from external sources such as project issues and documentation, which creates a surface for indirect prompt injection.
  • Ingestion points: Project documentation, GitHub issues, and source code files (SKILL.md).
  • Boundary markers: None explicitly defined to separate untrusted content from instructions.
  • Capability inventory: Execution of local build and test scripts via npm and Node.js (SKILL.md).
  • Sanitization: No sanitization steps for external data are described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 09:50 PM